Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Discussion snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erty
    -0.08
    ушки
    -0.07
    .NUM
    -0.07
    usted
    -0.07
     breeze
    -0.06
    .population
    -0.06
     Ft
    -0.06
    UST
    -0.06
    아서
    -0.06
    θή
    -0.06
    POSITIVE LOGITS
     против
    0.06
     dévelop
    0.06
     Mich
    0.06
    из
    0.06
    	entry
    0.06
     offic
    0.06
    	class
    0.06
     Macedonia
    0.06
    Ан
    0.06
     трен
    0.06
    Act Density 0.002%

    No Known Activations